A reverse Turing-test for predicting social deficits in people with Autism

Abstract

AbstractSocial symptoms of autism spectrum disorder (ASD) are typically viewed as consequences of an impaired Theory of Mind, i.e. the ability to understand others covert mental states. Here, we test the assumption that such \"mind blindness\" may be due to the inability to exploit contextual knowledge about, e.g., the stakes of social interactions, to make sense of otherwise ambiguous cues (e.g., idiosyncratic responses to social competition). In this view, social cognition in ASD may simply reduce to non-social cognition, i.e. cognition that is not informed by the social context. We compared 24 adult participants with ASD to 24 neurotypic participants in a repeated dyadic competitive game against artificial agents with calibrated mentalizing sophistication. Critically, participants were framed to believe that they were competing against humans (social framing) or not (non-social framing), hence the \"reverse Turing test\". In contrast to control participants, the strategy of people with ASD is insensitive to the games framing, i.e. they do not constrain their understanding of others behaviour with the contextual knowledge about the game (cf. competitive social framing). They also outperform controls when playing against simple agents, but are outperformed by them against recursive algorithms framed as human opponents. Moreover, computational analyses of trial-by-trial choice sequences in the game show that individuals with ASD rely on a distinctive cognitive strategy with subnormal flexibility and mentalizing sophistication. These computational phenotypes yield 79% diagnosis classification accuracy and explain 62% of the severity of social symptoms in people with ASD.